Search Results for author: Sam Devlin

Found 24 papers, 9 papers with code

UniMASK: Unified Inference in Sequential Decision Problems

1 code implementation20 Nov 2022 Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks.

Decision Making

You May Not Need Ratio Clipping in PPO

no code implementations31 Jan 2022 Mingfei Sun, Vitaly Kurin, Guoqing Liu, Sam Devlin, Tao Qin, Katja Hofmann, Shimon Whiteson

Furthermore, we show that ESPO can be easily scaled up to distributed training with many workers, delivering strong performance as well.

Continuous Control

Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO

no code implementations31 Jan 2022 Mingfei Sun, Sam Devlin, Jacob Beck, Katja Hofmann, Shimon Whiteson

Finally, our empirical results support the hypothesis that the strong performance of IPPO and MAPPO is a direct result of enforcing such a trust region constraint via clipping in centralized training, and the good values of the hyperparameters for this enforcement are highly sensitive to the number of agents, as predicted by our theoretical analysis.

Multi-agent Reinforcement Learning

Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning

1 code implementation30 Jul 2021 Robert Loftin, Aadirupa Saha, Sam Devlin, Katja Hofmann

High sample complexity remains a barrier to the application of reinforcement learning (RL), particularly in multi-agent systems.

Efficient Exploration Multi-agent Reinforcement Learning +1

Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation

1 code implementation20 May 2021 Sam Devlin, Raluca Georgescu, Ida Momennejad, Jaroslaw Rzepecki, Evelyn Zuniga, Gavin Costello, Guy Leroy, Ali Shaw, Katja Hofmann

A key challenge on the path to developing agents that learn complex human-like behavior is the need to quickly and accurately quantify human-likeness.

The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors

no code implementations26 Jan 2021 William H. Guss, Mario Ynocente Castro, Sam Devlin, Brandon Houghton, Noboru Sean Kuno, Crissman Loomis, Stephanie Milani, Sharada Mohanty, Keisuke Nakata, Ruslan Salakhutdinov, John Schulman, Shinya Shiroshita, Nicholay Topin, Avinash Ummadisingu, Oriol Vinyals

Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrinking segment of the AI community access to their development.

Decision Making Efficient Exploration +1

Evaluating the Robustness of Collaborative Agents

no code implementations14 Jan 2021 Paul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, A. D. Dragan, Rohin Shah

We apply this methodology to build a suite of unit tests for the Overcooked-AI environment, and use this test suite to evaluate three proposals for improving robustness.

Difference Rewards Policy Gradients

no code implementations21 Dec 2020 Jacopo Castellini, Sam Devlin, Frans A. Oliehoek, Rahul Savani

Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning.

Multi-agent Reinforcement Learning Policy Gradient Methods +1

"It's Unwieldy and It Takes a Lot of Time." Challenges and Opportunities for Creating Agents in Commercial Games

no code implementations1 Sep 2020 Mikhail Jacob, Sam Devlin, Katja Hofmann

We compare with literature from the research community that address the challenges identified and conclude by highlighting promising directions for future research supporting agent creation in the games industry.

Meta-Learning Divergences of Variational Inference

no code implementations6 Jul 2020 Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability.

Bayesian Inference Few-Shot Learning +3

AMRL: Aggregated Memory For Reinforcement Learning

no code implementations ICLR 2020 Jacob Beck, Kamil Ciosek, Sam Devlin, Sebastian Tschiatschek, Cheng Zhang, Katja Hofmann

In many partially observable scenarios, Reinforcement Learning (RL) agents must rely on long-term memory in order to learn an optimal policy.

reinforcement-learning

Rolling Horizon Evolutionary Algorithms for General Video Game Playing

1 code implementation27 Mar 2020 Raluca D. Gaina, Sam Devlin, Simon M. Lucas, Diego Perez-Liebana

Game-playing Evolutionary Algorithms, specifically Rolling Horizon Evolutionary Algorithms, have recently managed to beat the state of the art in win rate across many video games.

Meta-Learning for Variational Inference

no code implementations pproximateinference AABI Symposium 2019 Ruqi Zhang, Yingzhen Li, Chris De Sa, Sam Devlin, Cheng Zhang

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and general applicability.

Bayesian Inference Meta-Learning +3

Resource Abstraction for Reinforcement Learning in Multiagent Congestion Problems

no code implementations13 Mar 2019 Kleanthis Malialis, Sam Devlin, Daniel Kudenko

These are learning time, scalability and decentralised coordination i. e. no communication between the learning agents.

reinforcement-learning

The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition

2 code implementations23 Jan 2019 Diego Perez-Liebana, Katja Hofmann, Sharada Prasanna Mohanty, Noburu Kuno, Andre Kramer, Sam Devlin, Raluca D. Gaina, Daniel Ionita

Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types.

Multi-agent Reinforcement Learning reinforcement-learning

The Text-Based Adventure AI Competition

1 code implementation3 Aug 2018 Timothy Atkinson, Hendrik Baier, Tara Copplestone, Sam Devlin, Jerry Swan

In 2016, 2017, and 2018 at the IEEE Conference on Computational Intelligence in Games, the authors of this paper ran a competition for agents that can play classic text-based adventure games.

Board Games Natural Language Understanding

Domain Adaptation for Deep Reinforcement Learning in Visually Distinct Games

no code implementations ICLR 2018 Dino S. Ratcliffe, Luca Citi, Sam Devlin, Udo Kruschwitz

Many deep reinforcement learning approaches use graphical state representations, this means visually distinct games that share the same underlying structure cannot effectively share knowledge.

Domain Adaptation Multi-Task Learning +1

Win Prediction in Esports: Mixed-Rank Match Prediction in Multi-player Online Battle Arena Games

no code implementations17 Nov 2017 Victoria Hodge, Sam Devlin, Nick Sephton, Florian Block, Anders Drachen, Peter Cowling

Given the comparatively limited supply of professional data, a key question is thus whether mixed-rank match datasets can be used to create data-driven models which predict winners in professional matches and provide a simple in-game statistic for viewers and broadcasters.

Cannot find the paper you are looking for? You can Submit a new open access paper.